© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16464
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing high-quality customer service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inho
    -0.07
    ansa
    -0.07
    okoj
    -0.07
    rong
    -0.06
    fall
    -0.06
    bis
    -0.06
    erken
    -0.06
     Ago
    -0.06
    ombo
    -0.06
    asha
    -0.06
    POSITIVE LOGITS
    ypo
    0.07
     rencont
    0.07
    /service
    0.06
    683
    0.06
    /support
    0.06
    ability
    0.06
    basename
    0.06
    aint
    0.06
     Hip
    0.06
     levels
    0.06
    Activations Density 0.011%

    No Known Activations